The Loss-Averse Retailer’s Ordering Policy under Yield and Demand Uncertainty - Intelligent Computing for Sustainable Energy and Environment - page 203

The Loss-Averse Retailer's Ordering Policy
under Yield and Demand Uncertainty
Wei Liu 1 , 2 , Shiji Song 1 , ,andChengWu 1
1 Department of Automation, Tsinghua University, Beijing 100084, China
2 Department of Basic Science, Military Economics Academy, Wuhan 430035, China
[e-mail],
[e-mail],
[e-mail]
Abstract. This paper studies a single-period inventory problem with
random yield and demand. In general, most of the previous works are
based on the assumption of risk neutrality. We incorporate loss-averse
preferences into this problem and the retailer's objective is to maximize
the expected utility. We obtain the retailer's optimal ordering policy and
then investigate the impact of loss aversion on it. Especially, if the short-
age cost is small enough, the loss-averse retailer will always order less
than the risk-neutral one. Moreover, the impacts of price and cost pa-
rameters on the loss-averse retailer's optimal order quantity are analyzed.
Then numerical experiments are conducted to illustrate our results.
Keywords: Inventory, Loss aversion, Random yield.
1 Introduction
Inventory control under risk is one of the main subjects in supply chain man-
agement and interest in it remains unabated in recent decades. One of the as-
sumptions of the traditional models is that the quality of the product is perfect
and the lot produced or ordered does not contain any defective unit. However,
this is usually not the case in reality. Most production processes do not make
parts that are completely defect-free, e.g., the yield of chips in semiconductor
manufacturing is usually less than 50% ([1]). On the other hand, the lot the
retailer receives often contains some units that are spoiled or broken in transit
and then the quantity of good units is less than the quantity ordered. Such yield
uncertainty will cause the output or quantity received to be highly variable and
thus affect the production or ordering policy.
This phenomenon has received considerable attention and the production or
inventory problem with random yield has been studied in various contexts. The
review of the literature on this problem can be found in [2] and [3]. Gerchak et
al. [4] investigate both single-period and multi-period production models with
random yield. They obtain the optimal policy and show that it is not an order-up-
to policy. Wang and Gerchak [5] further extend the above model by considering